-
Automatic 3D object segmentation in multiple views using volumetric graph-cuts
-
Learning non-metric visual similarity for image retrieval
-
Video Normals from Colored Lights
We present an algorithm and the associated single-view capture methodology to acquire the detailed 3D shape, bends, and wrinkles of deforming surfaces. Moving 3D data has been difficult to obtain by methods that rely on known surface features, structured light,…
-
Self-calibrated, Multi-spectral Photometric Stereo for 3D Face Capture
-
Detection of multiple meaningful primitive geometric models
-
Our 3D Vision Data-Sets in the Making
-
A Deep Learning Approach to Automatic Caption Generation for News Images
Automatic caption generation of images has gained significant interest. It gives rise to a lot of interesting image-related applications. For example, it could help in image/video retrieval and management of vast amount of multimedia data available on the Internet. It…
-
An industrial system for vehicle tyre detection and text recognition using a pipeline of conventional image processing and deep learning
This paper presents an industrial system to readtext on tyre sidewalls. Images of vehicle tyres in motion areacquired using roadside cameras. Firstly, the tyre circularity isdetected using Circular Hough Transform (CHT) with dynamicradius detection. The tyre is then unwarped into…
-
和訳 コンピュータビジョンの最新動向と新たな応用 (特集 デジタルメディア処理先端技術)
-
Traffic3d: An Open-Source Traffic-Based Interactive Framework to Train Ai Agents